Commit History

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

8e0c378
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

8f140ab
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

c0a6843
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

245c45c
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

02d4666
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

afdcbef
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

7193b31
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

bfdd9dc
verified

sarel commited on Apr 13

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

7b9abb8
verified

sarel commited on Apr 13

Multi-tier risk scoring: strong/medium/weak features, 4-tier verdicts, delete+threshold UI

a24d8e7
verified

sarel commited on Apr 5

Multi-tier risk scoring: strong/medium/weak features, 4-tier verdicts, delete+threshold UI

42584cd
verified

sarel commited on Apr 5

UI: SAFE/UNSAFE badges, delete traces, threshold controls

b99e507
verified

sarel commited on Apr 5

UI: SAFE/UNSAFE badges, delete traces, threshold controls

18bbbf5
verified

sarel commited on Apr 5

UI: SAFE/UNSAFE badges, delete traces, threshold controls

14e03be
verified

sarel commited on Apr 5

Full update: circuit tracer integration, safety threshold, feature decoding, edges

a293618
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

4b911dc
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

8bfac15
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

4a1c639
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

c291940
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

9735f5a
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

2ccd89e
verified

sarel commited on Apr 1

Full update: circuit tracer integration, safety threshold, feature decoding, edges

862fbf1
verified

sarel commited on Apr 1

Fix: all features + edges + safety scoring

7dffb13
verified

sarel commited on Mar 31

Fix: all features + edges + safety scoring

92df347
verified

sarel commited on Mar 31

Fix: all features + edges + safety scoring

d0ef150
verified

sarel commited on Mar 31

Update src/frontend/CircuitAnalysisPanel.tsx - client-side safety scoring

b3ad74a
verified

sarel commited on Mar 31

Update src/backend/agent/circuit_integration.py - client-side safety scoring

098d3dd
verified

sarel commited on Mar 31

Update src/circuit_tracer/api.py - client-side safety scoring

50b0a00
verified

sarel commited on Mar 31

Add src/frontend/useChat.ts

f4695f3
verified

sarel commited on Mar 31

Add src/frontend/types.ts

2726408
verified

sarel commited on Mar 31

Add src/frontend/CircuitTracerDashboard.tsx

6110cd5
verified

sarel commited on Mar 31

Add src/frontend/CircuitAnalysisPanel.tsx

6d5fa74
verified

sarel commited on Mar 31

Add src/backend/routers/chat.py

e0ad9c2
verified

sarel commited on Mar 31

Add src/backend/agent/orchestrator.py

b649750
verified

sarel commited on Mar 31

Add src/backend/agent/circuit_integration.py

43aedf0
verified

sarel commited on Mar 31

Add src/circuit_tracer/visualization/export.py

0776aae
verified

sarel commited on Mar 31

Add src/circuit_tracer/visualization/init.py

39dd9ac
verified

sarel commited on Mar 31

Add src/circuit_tracer/interventions/steering.py

78b12d5
verified

sarel commited on Mar 31

Add src/circuit_tracer/interventions/init.py

d7b6419
verified

sarel commited on Mar 31

Add src/circuit_tracer/attribution/pruning.py

397f888
verified

sarel commited on Mar 31

Add src/circuit_tracer/attribution/replacement_model.py

225b19e
verified

sarel commited on Mar 31

Add src/circuit_tracer/attribution/graph.py

a037a68
verified

sarel commited on Mar 31

Add src/circuit_tracer/attribution/init.py

7548354
verified

sarel commited on Mar 31

Add src/circuit_tracer/transcoders/registry.py

b5efec6
verified

sarel commited on Mar 31

Add src/circuit_tracer/transcoders/vision_transcoder.py

a2cef74
verified

sarel commited on Mar 31

Add src/circuit_tracer/transcoders/cross_layer_transcoder.py

45d6b28
verified

sarel commited on Mar 31

Add src/circuit_tracer/transcoders/moe_transcoder.py

4af9caa
verified

sarel commited on Mar 31

Add src/circuit_tracer/transcoders/init.py

5456848
verified

sarel commited on Mar 31

Add src/circuit_tracer/saes/trainer.py

344a3ca
verified

sarel commited on Mar 31

Add src/circuit_tracer/saes/registry.py

d8878a6
verified

sarel commited on Mar 31

Commit History

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements 8e0c378 verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements 8f140ab verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements c0a6843 verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements 245c45c verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements 02d4666 verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements afdcbef verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements 7193b31 verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements bfdd9dc verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements 7b9abb8 verified

Multi-tier risk scoring: strong/medium/weak features, 4-tier verdicts, delete+threshold UI a24d8e7 verified

Multi-tier risk scoring: strong/medium/weak features, 4-tier verdicts, delete+threshold UI 42584cd verified

UI: SAFE/UNSAFE badges, delete traces, threshold controls b99e507 verified

UI: SAFE/UNSAFE badges, delete traces, threshold controls 18bbbf5 verified

UI: SAFE/UNSAFE badges, delete traces, threshold controls 14e03be verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges a293618 verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges 4b911dc verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges 8bfac15 verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges 4a1c639 verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges c291940 verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges 9735f5a verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges 2ccd89e verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges 862fbf1 verified

Fix: all features + edges + safety scoring 7dffb13 verified

Fix: all features + edges + safety scoring 92df347 verified

Fix: all features + edges + safety scoring d0ef150 verified

Update src/frontend/CircuitAnalysisPanel.tsx - client-side safety scoring b3ad74a verified

Update src/backend/agent/circuit_integration.py - client-side safety scoring 098d3dd verified

Update src/circuit_tracer/api.py - client-side safety scoring 50b0a00 verified

Add src/frontend/useChat.ts f4695f3 verified

Add src/frontend/types.ts 2726408 verified

Add src/frontend/CircuitTracerDashboard.tsx 6110cd5 verified

Add src/frontend/CircuitAnalysisPanel.tsx 6d5fa74 verified

Add src/backend/routers/chat.py e0ad9c2 verified

Add src/backend/agent/orchestrator.py b649750 verified

Add src/backend/agent/circuit_integration.py 43aedf0 verified

Add src/circuit_tracer/visualization/export.py 0776aae verified

Add src/circuit_tracer/visualization/__init__.py 39dd9ac verified

Add src/circuit_tracer/interventions/steering.py 78b12d5 verified

Add src/circuit_tracer/interventions/__init__.py d7b6419 verified

Add src/circuit_tracer/attribution/pruning.py 397f888 verified

Add src/circuit_tracer/attribution/replacement_model.py 225b19e verified

Add src/circuit_tracer/attribution/graph.py a037a68 verified

Add src/circuit_tracer/attribution/__init__.py 7548354 verified

Add src/circuit_tracer/transcoders/registry.py b5efec6 verified

Add src/circuit_tracer/transcoders/vision_transcoder.py a2cef74 verified

Add src/circuit_tracer/transcoders/cross_layer_transcoder.py 45d6b28 verified

Add src/circuit_tracer/transcoders/moe_transcoder.py 4af9caa verified

Add src/circuit_tracer/transcoders/__init__.py 5456848 verified

Add src/circuit_tracer/saes/trainer.py 344a3ca verified

Add src/circuit_tracer/saes/registry.py d8878a6 verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

8e0c378
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

8f140ab
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

c0a6843
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

245c45c
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

02d4666
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

afdcbef
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

7193b31
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

bfdd9dc
verified

Latest: synthetic data generator with data_exfiltration, tiered scoring refinements

7b9abb8
verified

Multi-tier risk scoring: strong/medium/weak features, 4-tier verdicts, delete+threshold UI

a24d8e7
verified

Multi-tier risk scoring: strong/medium/weak features, 4-tier verdicts, delete+threshold UI

42584cd
verified

UI: SAFE/UNSAFE badges, delete traces, threshold controls

b99e507
verified

UI: SAFE/UNSAFE badges, delete traces, threshold controls

18bbbf5
verified

UI: SAFE/UNSAFE badges, delete traces, threshold controls

14e03be
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

a293618
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

4b911dc
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

8bfac15
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

4a1c639
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

c291940
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

9735f5a
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

2ccd89e
verified

Full update: circuit tracer integration, safety threshold, feature decoding, edges

862fbf1
verified

Fix: all features + edges + safety scoring

7dffb13
verified

Fix: all features + edges + safety scoring

92df347
verified

Fix: all features + edges + safety scoring

d0ef150
verified

Update src/frontend/CircuitAnalysisPanel.tsx - client-side safety scoring

b3ad74a
verified

Update src/backend/agent/circuit_integration.py - client-side safety scoring

098d3dd
verified

Update src/circuit_tracer/api.py - client-side safety scoring

50b0a00
verified

Add src/frontend/useChat.ts

f4695f3
verified

Add src/frontend/types.ts

2726408
verified

Add src/frontend/CircuitTracerDashboard.tsx

6110cd5
verified

Add src/frontend/CircuitAnalysisPanel.tsx

6d5fa74
verified

Add src/backend/routers/chat.py

e0ad9c2
verified

Add src/backend/agent/orchestrator.py

b649750
verified

Add src/backend/agent/circuit_integration.py

43aedf0
verified

Add src/circuit_tracer/visualization/export.py

0776aae
verified

Add src/circuit_tracer/visualization/init.py

39dd9ac
verified

Add src/circuit_tracer/interventions/steering.py

78b12d5
verified

Add src/circuit_tracer/interventions/init.py

d7b6419
verified

Add src/circuit_tracer/attribution/pruning.py

397f888
verified

Add src/circuit_tracer/attribution/replacement_model.py

225b19e
verified

Add src/circuit_tracer/attribution/graph.py

a037a68
verified

Add src/circuit_tracer/attribution/init.py

7548354
verified

Add src/circuit_tracer/transcoders/registry.py

b5efec6
verified

Add src/circuit_tracer/transcoders/vision_transcoder.py

a2cef74
verified

Add src/circuit_tracer/transcoders/cross_layer_transcoder.py

45d6b28
verified

Add src/circuit_tracer/transcoders/moe_transcoder.py

4af9caa
verified

Add src/circuit_tracer/transcoders/init.py

5456848
verified

Add src/circuit_tracer/saes/trainer.py

344a3ca
verified

Add src/circuit_tracer/saes/registry.py

d8878a6
verified